System, apparatus, and method for misalignment-based remaining useful life estimation of bearings
By monitoring and analyzing the operating data of the electric machine in real time, detecting misalignment values using virtual models and regression models, predicting the remaining useful life of the bearing, solving the problem of inability to detect misalignment severity in real time in the prior art, and achieving the correctness of the correctness Accurate life forecast and operational efficiency improvement of electric machine bearings.
Patent Information
- Application Number
- CN202380032434.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-03-30
- Filing Date
- 2023-03-20
- Publication Date
- 2024-12-03
AI Technical Summary
The prior art cannot detect and estimate the severity of misalignment of bearings at the drive end of the electric machine in real time, resulting in the inability to accurately predict the remaining useful life of the bearing, affecting the normal operation of the motor.
By monitoring the operating data of the electric machine in real time, analyzing current, vibration and thermal characteristics, detecting misaligned values using virtual model simulation and regression models, and predicting the remaining useful life of the bearing based on the misaligned force model, providing real-time notification and control parameters Adjustment.
Real-time detection and life prediction of bearing misalignment of electric machines are achieved, downtime is reduced, operational efficiency and reliability of the motor are improved, and manual intervention is avoided.
Smart Images

Figure CN119072616A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to estimation of remaining useful life, and in particular to systems and methods for estimating remaining useful life of bearings. Background Art
[0002] Typically, large motors are directly coupled to the corresponding load using rigid or flexible couplings. Rigid couplings do not compensate for misalignment between the motor and the driven equipment (i.e., the load). Flexible couplings can tolerate misalignment to a certain extent. Flexible couplings can also reduce vibrations transmitted from the motor to the load, and vice versa. In addition, some flexible couplings can also insulate the pivot of the driven equipment from stray currents.
[0003] Although flexible couplings reduce vibration shock to some extent, dynamic forces generated by misalignment of the motor and driven equipment can severely impact the motor's drive-end bearing. The severity of the shock to the drive-end bearing can also vary based on whether the misalignment is parallel or angular in nature. Misalignment can be due to thermal expansion of the coupling or due to pre-alignment errors of the motor and driven equipment prior to operation.
[0004] Prior art does not allow for the detection and estimation of the severity of misalignments during operation of the electric machine and driven equipment. Typically, such misalignments are detected during maintenance phases and the severity of the misalignments estimated, resulting in additional downtime. Furthermore, unnoticed misalignments seriously affect the remaining useful life of the bearings, and thus ultimately the operation of the electric motor. In view of the above, there is a need for estimating the severity of the misalignments online and determining the remaining useful life of the drive end bearing based on the estimated misalignments. Summary of the invention
[0005] In view of the foregoing, a need exists for real-time estimation of the remaining useful life of a bearing based on misalignment.
[0006] It is therefore an object of the present invention to provide a system, apparatus and method for misalignment-based remaining useful life estimation of electric machine bearings.
[0007] The objects of the present invention are achieved by a method for estimating the remaining useful life of an electric machine bearing as disclosed herein. The electric machine is operable to transfer rotational energy to a load via a pivot supported by the bearing. The method comprises obtaining, in real time from one or more sources, operational data associated with the electric machine and indicating misalignment of the pivot.
[0008] Advantageously, the present invention facilitates estimating the remaining useful life of a bearing in real time during operation of an electric machine, ie, via online monitoring.
[0009] The method further includes analyzing the operational data to detect misalignment of the electric machine pivot. In an embodiment, detecting misalignment of the electric machine pivot based on the operational data includes calculating a characteristic feature of the electric machine based on the operational data. In an embodiment, the characteristic feature is at least one of a current feature, a vibration feature, and a thermal feature. In a further embodiment, the characteristic feature is generated from the operational data using one or more transformation functions. In an alternative embodiment, the characteristic feature is generated based on the operational data using a regression model. In addition, the characteristic feature is analyzed to detect misalignment of the pivot.
[0010] Advantageously, the regression model provides an alternative to sensorless measurement of operating parameters and eliminates the need for multiple sensors for multiple operating parameter measurements.
[0011] The method further includes simulating the real-time behavior of at least the electric machine using the virtual model of at least the electric machine to achieve a simulation result indicating a misalignment value corresponding to the misalignment of the pivot when the misalignment is detected. In an embodiment, simulating the real-time behavior of at least the electric machine using the virtual model of at least the electric machine to achieve a simulation result indicating a misalignment value corresponding to the misalignment of the pivot includes dynamically updating the virtual model of the electric machine based on the operational data when the misalignment is detected. In addition, configuring a machine executable simulation instance of at least the electric machine based on the updated virtual model. In addition, executing the configured simulation instance in a simulation environment to generate a simulation result.
[0012] Advantageously, the misalignment value is determined via a simulation based on a virtual model. As a result, human intervention can be eliminated in estimating the misalignment. Furthermore, the present invention helps quantify misalignment during operation of the electric machine, in contrast to prior art techniques which only help detect the results of the misalignment.
[0013] The method further includes predicting a remaining useful life of the bearing based on the misalignment value. In an embodiment, predicting the remaining useful life of the bearing based on the misalignment value includes calculating a dynamic misalignment force on the bearing in real time based on the misalignment value using a predetermined misalignment force model. In addition, a rated life model of the bearing is dynamically configured based on the calculated dynamic misalignment force. The remaining useful life of the bearing is further predicted using the configured rated life model. The method further includes generating a notification on an output device indicating the predicted remaining useful life of the bearing.
[0014] Advantageously, the present invention facilitates continuous determination of the impact of misalignment on the remaining useful life of a bearing through real-time monitoring of operating parameters such as current signatures or vibration signatures and simulation results.
[0015] In an embodiment, the method further comprises adjusting at least one control parameter of the electric machine using the predicted remaining useful life of the bearing.In an embodiment, the at least one control parameter is adjusted to modify at least one of a speed and a load of the electric machine.
[0016] According to an embodiment of the present invention, a device for estimating the remaining useful life of a bearing is also disclosed herein. The device includes one or more processing units, and a memory unit operably coupled to the one or more processing units. The memory unit includes a bearing monitoring module stored in the form of machine-readable instructions executable by the one or more processing units. The bearing monitoring module is configured to perform the above method steps.
[0017] According to an embodiment of the present invention, a system for estimating the remaining useful life of a bearing is also disclosed herein. The system includes one or more sources capable of providing operating data associated with the bearing and the device as described above, and is communicatively coupled to the one or more sources. The term "source" as used herein refers to an electronic device configured to obtain operating data and transmit it to the device. Non-limiting examples of sources include sensing units, controllers, and edge devices.
[0018] The object of the present invention is also achieved through a computer-readable medium, on which a program code segment of a computer program is stored, which can be loaded into a processor and / or executed by a processor. When the program code segment is executed, the processor executes the method as described above.
[0019] Implementing the present invention by means of a computer program product and / or a non-transitory computer-readable storage medium has the advantage that a computer system can be easily adapted by installing the computer program in order to work according to the proposals of the present invention.
[0020] The computer program product may be, for example, a computer program or include another element in addition to the computer program. The other element may be hardware, such as a memory device on which the computer program is stored, a hardware key for using the computer program, etc., and / or software, such as a document or software key for using the computer program.
[0021] The present invention also discloses a computer program having machine-readable instructions, which, when executed by one or more computing devices, cause the one or more computing devices to perform the method according to the above method steps. Also disclosed is a machine-readable storage medium including the computer program described above.
[0022] The above-mentioned properties, features and advantages of the present invention and the manner of achieving them will become more clear and understandable (clear) through the following description of the embodiments of the present invention in conjunction with the corresponding drawings. The illustrated embodiments are intended to illustrate, rather than limit, the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The invention is further described below with reference to the illustrative embodiments shown in the accompanying drawings, in which:
[0024] Figure 1A illustrates a block diagram of a system for estimating the remaining useful life of a bearing associated with an electric machine 105 according to an embodiment of the present invention;
[0025] Figure 1B A block diagram of an apparatus for estimating the remaining useful life of a bearing associated with an electric machine 105 according to an embodiment of the present invention is illustrated;
[0026] Figure 2 The diagram shows the structure of a ball bearing;
[0027] Figure 3A An electric motor coupled to a pump is illustrated;
[0028] Figure 3B illustrates a test setup for generating experimental data associated with an electric motor according to an embodiment of the present invention;
[0029] Figure 4 A flow chart of a method for estimating a bearing RUL according to an embodiment of the present invention is shown;
[0030] Figure 5 A graphical user interface 500 is shown which displays an example of a current spectrum generated based on a current signature of a motor;
[0031] Figure 6 shows a workflow for estimating the RUL of a motor drive end bearing according to an exemplary embodiment of the present invention; and
[0032] Figure 7 A workflow for estimating the RUL of a motor drive end bearing according to another exemplary embodiment of the present invention is illustrated. DETAILED DESCRIPTION
[0033] Embodiments for practicing the present invention are described in detail below. Various embodiments are described with reference to the accompanying drawings, wherein the same reference numerals are used to refer to the same elements throughout. In the following description, for the purpose of explanation, many specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be apparent that such embodiments may be practiced without these specific details.
[0034] Figure 1AA block diagram of a system 100 for estimating the remaining useful life (RUL) of a bearing 102 associated with an electric machine 105 is illustrated in accordance with an embodiment of the present invention. Non-limiting examples of electric machines may include AC generators, DC generators, AC motors, DC motors, permanent magnet machines, induction machines, and brushed machines. The electric machine 105 is mechanically coupled to a load, i.e., driven equipment, via a coupler (not shown). More specifically, the coupler mechanically couples a pivot 107 of the electric machine 105 to the load to enable transfer of rotational energy.
[0035] The bearing 102 is a mechanical component suitable for supporting the load applied to the pivot 107 of the electric machine 105 and allowing the rotational movement of the pivot within the support structure. Non-limiting examples of bearings include deep groove ball bearings, cylindrical roller bearings, tapered roller bearings, thrust bearings, angular contact ball bearings, needle ball bearings, etc. The system 100 is configured to estimate the RUL of the bearing 102 based on the misalignment of the pivot.
[0036] In an embodiment, the bearing 102 includes an inner ring, an outer ring, and a plurality of rolling elements disposed in a gap between the inner ring and the outer ring. The bearing 102 further includes a cage positioned between the inner ring and the outer ring for maintaining a symmetrical radial gap between the rolling elements. Examples of the bearing 102 are referenced later in this disclosure. Figure 2 describe.
[0037] The system 100 includes an apparatus 110 communicatively coupled to one or more edge devices 115 via a network 120. The network 120 may include, for example, a local area network (LAN), a wide area network (WAN), Wi-Fi, etc. The edge device 115 is configured to receive operational data from at least one sensing unit 125 associated with the electric machine 105.
[0038] The sensing unit 125 generates an output signal indicative of an operating parameter associated with the electric machine 105 in real time. In a preferred embodiment, the sensing unit 125 may include a current transformer configured to output an electrical signal corresponding to a current characteristic associated with the electric machine 105. The current characteristic includes a time series current signal. In another embodiment, the sensing unit 125 may include a vibration sensor configured to generate an electrical signal corresponding to a vibration characteristic of the electric machine 105. The vibration characteristic may include a time domain acceleration signal or a velocity signal. In yet another embodiment, the sensing unit 125 may include a temperature sensor configured to generate an electrical signal corresponding to a thermal characteristic associated with the electric machine 105. The thermal characteristic may include a time domain temperature signal.
[0039] The sensing unit 125 is further communicatively coupled to the apparatus 110. In an embodiment, the operational data is obtained through a data acquisition interface associated with the edge device 115. The edge device 115 provides the operational data to the apparatus 110 in real time. In addition, the edge device 115 is also configured to provide one or more bearing parameters associated with the bearing 102 to the apparatus 110. The one or more bearing parameters may be stored in a memory of the edge device 115, or may be input to the edge device 115 by an operator. For example, the edge device 115 may be communicatively coupled to a client device 130. Non-limiting examples of client devices include personal computers, workstations, personal digital assistants, and human-machine interfaces. The client device 130 may enable an operator to input values of one or more bearing parameters through a web-based interface. When one or more bearing parameters are received from the operator, the edge device 115 transmits a request to the apparatus 110 for estimating the RUL of the bearing 102.
[0040] The one or more bearing parameters include, but are not limited to, a standard bearing number, ball size, bearing static load, material density, angular velocity, internal clearance, bearing diameter, number of rolling elements, rolling element radius, inner ring diameter, outer ring diameter, fatigue load limit, and type of lubricant used in the bearing 102. It must be understood that the standard bearing number indicates certain specifications such as ball size, bearing static load, material density, internal clearance, bearing diameter, number of rolling elements, rolling element radius, inner ring diameter, outer ring diameter, fatigue load limit, bearing width, etc. as provided by the manufacturer of the bearing 102. Therefore, in an embodiment, a standard bearing number associated with the bearing 102 may be provided instead of explicitly providing the bearing parameters mentioned above.
[0041] The RUL of the bearing 102 may be affected by defects due to the initiation of failure modes in the bearing 102. Non-limiting examples of failure modes include spalling, pitting, plastic deformation, wear, galvanic erosion, and corrosion, typically on the outer race of the bearing 102. Some defects may occur due to misalignment of the pivot, eccentricity of the pivot, loose legs, the presence of contaminants, or due to the nature of the lubricant used within the bearing 102.
[0042] In this embodiment, the device 110 is deployed in a cloud computing environment. As used herein, a "cloud computing environment" refers to a processing environment that includes configurable computing physical and logical resources, such as networks, servers, storage, applications, services, etc., and data distributed via a network 120 (e.g., the Internet). The cloud computing environment provides on-demand network access to a shared pool of configurable computing physical and logical resources. The device 110 includes a bearing monitoring module that estimates the RUL of a given bearing based on corresponding operational data. Hereinafter, the term "operational data" may be understood to include the output of at least one sensing unit 125, bearing parameters, and load specifications. Additionally, the device 110 may include a network interface for communicating with an edge device 115 via the network 120.
[0043] The device 110 includes a processing unit 135, a memory unit 140, a storage unit 145, a communication unit 150, a network interface 155 and a standard interface or bus 160, such as Figure 1B . Device 110 may be a computer, a workstation, a virtual machine running on host hardware, a microcontroller, or an integrated circuit. Alternatively, device 110 may be a real or virtual group of computers (the technical term for a real group of computers is a "cluster" and the technical term for a virtual group of computers is a "cloud").
[0044] As used herein, the term "processing unit" 135 means any type of computing circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a graphics processor, a digital signal processor, or any other type of processing circuit. Processing unit 135 may also include an embedded controller, such as a general or programmable logic device or array, an application specific integrated circuit, a single chip computer, etc. In general, processing unit 135 may include hardware elements and software elements. Processing unit 135 may be configured for multithreading, that is, processing unit 135 may host different computing processes simultaneously, execute in parallel, or switch between active and passive computing processes.
[0045] The memory unit 140 may be a volatile memory and a non-volatile memory. The memory unit 140 may be coupled for communication with the processing unit 135. The processing unit 135 may execute instructions and / or codes stored in the memory unit 140. A variety of computer-readable storage media may be stored in the memory unit 140 and may be accessed from the memory unit 140. The memory unit 140 may include any suitable element for storing data and machine-readable instructions, such as a read-only memory, a random access memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a hard drive, a removable media drive for processing optical disks, digital video disks, magnetic disks, tape cassettes, memory cards, etc.
[0046] The memory unit 140 includes a bearing monitoring module 165 in the form of machine-readable instructions on any of the above-mentioned storage media and can communicate with and be executed by the processing unit 135. The bearing monitoring module 165 includes a pre-processing module 170, an analysis module 175, a simulation module 180, a life estimation module 185, and a notification module 190. The pre-processing module 170 is configured to obtain operational data associated with the electric machine 105 in real time from one or more sources. The sources include the edge device 115, one or more sensing units 125, and the client device 130. The analysis module 175 is configured to analyze the operational data to detect misalignment of the pivot of the electric machine 105. The simulation module 180 is configured to simulate the real-time behavior of at least the electric machine 105 based on the virtual model when the misalignment is detected to generate a simulation result. The life estimation module 185 is configured to predict the RUL of the bearing 102 based on the misalignment value. The notification module 190 is configured to generate a notification indicating the predicted RUL of the bearing 102 on an output device. In this embodiment, the output device may be the client device 130 .
[0047] The storage unit 145 includes a non-volatile memory that stores default bearing parameters associated with standard bearing numbers. The storage unit 145 includes a database 195 that includes default values for bearing parameters, lookup tables corresponding to control parameters for different applications, predefined mathematical models corresponding to different types of bearings, and one or more lookup tables that include predetermined values for factors that vary with the operating conditions of the bearing 102. The bus 160 serves as an interconnection between the processing unit 135, the memory unit 140, the storage unit, and the network interface 155. The communication unit 150 enables the device 110 to receive requests from the edge device 115. The communication module can support different standard communication protocols, such as transmission control protocol / Internet protocol (TCP / IP), Profinet, Profibus, and Internet Protocol version (IPv4).
[0048] One of ordinary skill in the art will appreciate that Figure 1A and Figure 1B The hardware depicted in the may vary for different implementations. For example, other peripheral devices such as optical drives, local area network (LAN) / wide area network (WAN) / wireless (e.g., Wi-Fi) adapters, graphics adapters, disk controllers, input / output (I / O) adapters, network connection devices may also be used in addition to or in place of the depicted hardware. The depicted examples are provided for purposes of explanation only and are not meant to imply architectural limitations with respect to the present disclosure.
[0049] Hereinafter, the present invention is explained in detail by considering a coupling system, wherein, for ease of explanation, the electric machine 105 is an electric motor and the load is a pump. The bearing is, for example, a ball bearing mounted on a motor pivot.
[0050] Figure 2 The structure of the ball bearing 200 is shown in the figure. The ball bearing 200 includes an outer ring 210 with a diameter D, and each of the outer rings has a radius r. ball The plurality of balls 215, the cage 220 and the inner ring 225 of diameter d are arranged in the gap between the outer ring 210 and the inner ring 225. The cage 220 maintains the symmetrical radial spacing between the balls 215. α is the contact angle between the balls and the outer ring. Here, d m is the pitch circle diameter of the bearing 200 .
[0051] Figure 3A and Figure 3B A test setup 300 is illustrated for generating experimental data associated with an electric motor 305 in accordance with an embodiment of the present invention. The experimental data is used to build a virtual model of the electric motor 305.
[0052] The virtual model can be based on one or more of a physics-based model, a computer-aided design (CAD) model, a computer-aided engineering (CAE) model, a one-dimensional (1D) model, a two-dimensional (2D) model, a three-dimensional (3D) model, a finite element (EE) model, a descriptive model, a metamodel, a stochastic model, a parametric model, a reduced-order model, a statistical model, a heuristic model, a predictive model, an aging model, a machine learning model, an artificial intelligence model, a deep learning model, a system model, an agent model, and the like.
[0053] The motor 305 is coupled to the pump 310 via the coupler 315 to form a coupled system, as in Figure 3A Hereinafter, the pivot 320 of the motor 305 may be interchangeably referred to as the drive pivot 320 or simply as the "pivot 320", and the pivot 325 of the pump 310 is specifically referred to as the driven pivot 325. Figure 3BAs indicated in FIG. 3 , the drive pivot 320 is mounted inside the housing 330 of the motor 305 using a suitable support structure. In addition, a drive end bearing 335 is provided between the support structure and the drive pivot 320 to guide the movement of the drive pivot 320 and prevent vibration when a load is applied to the drive pivot 320 (i.e., when the driven pivot 325 is coupled).
[0054] The test setup 300 includes one or more current transformers 340 mounted on the housing 330 of the motor 305. The current transformers 340 are configured to generate current signatures associated with the motor 305. The setup further includes one or more vibration sensors 345 mounted on the drive pivot 320 to measure vibration signals associated with the coupler 315. The outputs from the one or more current transformers 340 and the one or more vibration sensors 345 are further provided to an apparatus 350 (similar to the apparatus 110) as experimental data, as shown in FIG. Figure 3B The device 350 may further execute one or more machine-readable instructions to construct a virtual model, as explained in detail below.
[0055] In an embodiment, the virtual model may include any virtual representation, such as a digital twin, that serves as a real-time digital counterpart of the coupled system. In this embodiment, the virtual model is constructed based on current signatures and vibration signatures. Similarly, other operating parameters like thermal signatures may also be used to construct the virtual model. In this embodiment, the virtual model includes one or more regression models that relate at least one operating parameter of the motor 305 to one or more other operating parameters of the motor 305.
[0056] In order to construct the virtual model, first, experimental data associated with current characteristics, vibration characteristics, and thermal characteristics can be generated for a predefined set of operating conditions of the motor 305. In the present embodiment, the predefined operating conditions include at least one of a predefined load and a misalignment value. For example, the predefined operating conditions may include a combination of a load (e.g., 50%, 60%, 70%, 90%, 95%, etc. of full load capacity) and a misalignment value (e.g., 0.1 mm, 0.2 mm, 0.3 mm, 0.4 mm, etc.). In addition, the misalignment may be one of an angular misalignment, a radial misalignment, or a parallel misalignment. More specifically, the misalignment is artificially introduced into the motor 305 by displacing the drive pivot 320 by a value equal to a specific misalignment value and / or an alignment angle. The experimental data thus generated are further used to construct a virtual model of the coupled system. The virtual model may be further calibrated based on a test data set. The virtual model thus constructed is suitable for predicting misalignment values based on a given set of operating conditions.
[0057] Those skilled in the art will appreciate that the misalignment in the coupler 315 depends on the stiffness of the coupler 315. In order to improve the simulation speed, a reduced-order model of the coupler 315 can be used. For example, the coupler 315 can be modeled as a pseudo-bearing. The equivalent radial stiffness of the pseudo-bearing can be predetermined using finite element analysis (FEA) techniques. For example, the coupler 315 can be modeled as a pseudo-bearing with a specific overall stiffness, and the equivalent radial stiffness of the pseudo-bearing can be estimated using two-dimensional (2D) FEA and / or three-dimensional (3D) FEA. In another embodiment, the model of the pseudo-bearing can be configured based on the specifications associated with the coupler 315 supplied by the manufacturer. Non-limiting examples of the specifications supplied by the manufacturer include weight, torsional stiffness, inertia, maximum aperture, axial deflection, angular deflection, etc.
[0058] The experimental data can also be used to build a regression model that relates at least one operating parameter to at least another operating parameter of the motor 305. A regression algorithm is a type of supervised learning in machine learning (ML) that helps map a predictive relationship between dependent and independent variables. The regression algorithm can be one of linear regression and nonlinear regression.
[0059] The linear regression algorithm generates a machine learning model (hereinafter referred to as a linear regression model) that assumes a linear relationship between the dependent variable and the independent variable. Non-limiting examples of linear regression algorithms include ridge regression, neural network regression, and lasso regression. On the other hand, the nonlinear regression algorithm generates a machine learning model (nonlinear regression model) that uses a nonlinear relationship to relate the dependent variable to the independent variable. The nonlinear regression model can be based on, for example, logarithmic functions, trigonometric functions, exponential functions, power functions, Lorenz curves, Gaussian functions, etc. It must be understood by those of ordinary skill in the art that the nonlinear regression model is developed by a series of iterative approximations based on methods such as the Gauss-Newton method, the Levenberg-Marquardt method, etc. It must also be understood that the nonlinear regression model can be approximated as a linear regression model using standard techniques known to those skilled in the art.
[0060] In linear regression, the linear regression model is iteratively trained until the loss function is minimized. The loss function is calculated as follows:
[0061] Loss function: (simulation output - actual output) 2 (1)
[0062] Where the “simulated output” is the output predicted by the linear regression model for a given set of conditions, and the “actual output” is the output generated by one or more sensing units for the same set of conditions.
[0063] In nonlinear regression, a nonlinear regression model is generated based on the "sum of squares" function. The sum of squares (SS) function is used to identify the relationship that best fits a given experimental data set. More specifically, the best fitting relationship minimizes the SS function for a given regression model. For a set X of n items:
[0064]
[0065] Among them, X i is the i-th item in the set;
[0066] is the mean of all items in the set; and
[0067] is the deviation of each term from the mean.
[0068] The regression model thus generated is further calibrated based on test data including actual outputs generated by the sensing units 340 and 345. In other words, the regression model is calibrated to further reduce the deviation between the simulated output and the actual output of the regression model.
[0069] In a preferred embodiment, at least one regression model that relates the current characteristics of the motor 305 to the vibration characteristics is generated based on experimental data. In the example, at least one advanced signal processing technique can be used to extract features from each of the vibration characteristics and current characteristics measured using the sensing units 340 and 345. Non-limiting examples of extracted features include RMS, kurtosis, crest factor, and peak value. Non-limiting examples of advanced signal processing techniques include, but are not limited to, fast Fourier transform, continuous wavelet transform, discrete wavelet transform, and spectral kurtosis. In addition, the corresponding extracted features of the current characteristics and vibration characteristics for the same set of operating conditions are used to generate a regression model as described above. Similarly, a second regression model that relates the current characteristics to the thermal characteristics, a third regression model that associates the vibration characteristics with the thermal characteristics, and the like can be generated.
[0070] It must be understood that a regression model may be generated and calibrated in a manner similar to that described above, using linear or nonlinear regression, for any set of operating parameters associated with the motor 305. The regression model thus generated is used together with a virtual model of the coupled system to simulate the behavior of the motor 305 or coupled system during operation in a simulation environment.
[0071] Figure 4 FIG. 4 is a flow chart of a method 400 for estimating the RUL of a bearing 102 according to an embodiment of the present invention. The method includes steps 405 to 420. Figure 1A and 1B , method 400 is explained with reference to an electric motor coupled to a pump.
[0072] At step 405, operational data associated with the electric machine 105 and indicating a misalignment of the pivot 107 is obtained in real time from one or more sources associated with the electric machine 105. It must be understood that the term "real time" as used herein corresponds to an operational phase of the electric machine 105. The sources include the edge device 115, one or more sensing units 125, and the client device 130. The electric machine 105 is configured to transfer rotational energy to a load via a pivot supported by the bearing 102. In the case of an electric motor, the pivot of the motor is coupled to a pump via a coupler to enable the transfer of rotational energy from the motor to the pump. The operational data includes at least one of current data, vibration data, and thermal data corresponding to the motor.
[0073] At step 410, the operational data is analyzed to detect misalignment of the pivot of the electric machine 105. In an embodiment, characteristic features of the electric machine 105 are calculated based on the operational data. The real-time operational data can be represented in a time series format, or can be transformed to other domains using a transformation function such as a continuous wavelet transform, a discrete wavelet transform, or a fast Fourier transform. In this example, the operational data associated with the motor may include at least one of current data, vibration data, and thermal data. Accordingly, the characteristic features may include current features, vibration features, thermal features, etc. It must be understood that the characteristic features may include representations of the operational data in the time domain or the frequency domain. As a result, the characteristic features may also include spectra, such as current spectra, vibration spectra, and thermal radiation spectra.
[0074] In an embodiment, one or more characteristic features are indirectly derived from the operational data using a regression model. For example, a first regression model as explained with reference to FIG. 3 can be used to determine at least one feature corresponding to a vibration feature of the motor based on a current feature obtained from one or more sensing units 125. In an embodiment, the first regression model can generate a set of data points on a predefined interval from data points in the current feature, the set of data points forming a vibration feature associated with the motor.
[0075] The calculated characteristic features are analyzed to detect misalignment of the pivot 107. In this example, the misalignment may be caused by misalignment of the driving pivot 107 of the motor and the driven pivot of the pump. The presence of the misalignment is further detected by first generating a vibration spectrum of the motor. The vibration spectrum is generated by applying a fast Fourier transform to the time series vibration signal obtained from one or more sensing units 125. In addition, the misalignment is detected based on the presence of peaks (e.g., 2X and 3X peaks) in the vibration spectrum. Similarly, the peaks of the motor current spectrum generated by applying a transform function to the current signal obtained from one or more sensing units 125 can also be analyzed to detect misalignment.
[0076] At step 415, the virtual model of at least the electric machine 105 is used to simulate the real-time behavior of at least the electric machine 105 to achieve a simulation result indicating a misalignment value corresponding to the misalignment of the pivot 107 when a misalignment of the pivot 107 is detected. The simulation result indicates a misalignment value corresponding to the misalignment of the pivot 107. More specifically, the simulated misalignment value corresponds to the actual misalignment value of the pivot 107 because the virtual model is configured to simulate the real-time behavior of the motor 105. The misalignment value can be defined as a radial distance between at least one reference point on the pivot 107 and at least one point on the motor housing measured radially. For example, the reference points can be located at both ends of the pivot 107 inside the motor housing. In the case of parallel misalignment, the misalignment value is not equal to zero, but is constant over time. In the case of angular misalignment, the misalignment value varies over time. For example, the misalignment value can be 0.1 mm, 0.15 mm, 0.23 mm, 0.19 mm, etc.
[0077] In a preferred embodiment, the virtual model is a digital twin of the coupled system running on the edge device 115. In an embodiment, estimating the misalignment value based on the virtual model includes dynamically updating the virtual model of at least the electric machine 105 based on operational data obtained in real time. Here, the operational data may also include bearing parameters provided by the edge device 115 and specifications of the load applied to the pivot 107 by the pump. In addition, a machine executable simulation instance of at least the electric machine is configured based on the updated virtual model. The simulation instance is further executed in a simulation environment to generate simulation results. The simulation results indicate the misalignment value of the coupler in real time. The misalignment value is a numerical value indicating the severity of the misalignment at the coupler. The misalignment value may indicate a radial misalignment, an angular misalignment, or a parallel misalignment between the drive pivot 107 and the driven pivot.
[0078] At step 420, the RUL of the bearing 102 is predicted based on the misalignment value. In an example, the RUL can be expressed as the number of revolutions before failure occurs. In another example, the RUL is expressed as the number of hours of operation at a constant speed before failure. In a preferred embodiment, the rating life model as shown in equation (3) is dynamically configured based on the dynamic misalignment force:
[0079]
[0080] Among them, a iSO is the life correction factor based on a systematic approach to life calculation and is given by:
[0081]
[0082] Among them, a 1 is the reliability life correction factor, C u is the fatigue load limit in Newtons, ec is a contamination factor specific to the defect size, P is the dynamic equivalent radial load in Newtons, C is the dynamic equivalent radial load rating, and K is the viscosity ratio. Here, the dynamic parameter used to configure the rated life model is the dynamic equivalent radial load P or the dynamic misalignment force. The dynamic misalignment force corresponding to the misalignment value is calculated using a misalignment force model. The misalignment force model is a predetermined mathematical model that relates the misalignment value to the dynamic misalignment force. In an exemplary embodiment, the misalignment force model can resolve the force and moment components along the X, Y, and Z axes at the coupler based on the simulated misalignment value.
[0083] The reliability life correction factor is a predefined value specified in ISO 281:2007 for a given reliability value. For example, if the reliability can be considered to be 90%, al is taken as 1. By default, the reliability value is taken as 90%. In an embodiment of the present disclosure, the reliability value can be modified by an operator through a client device. Based on the reliability value, the reliability life correction factor can be further obtained from a first lookup table stored in the database 195. The fatigue load limit and the dynamic equivalent radial load rating are obtained from one or more bearing parameters associated with the bearing 102.
[0084] At step 425, a notification indicating the RUL may also be generated on an output device. For example, a text notification indicating the RUL of the bearing 102 along with the misalignment value may be generated in real time on a user interface. The notification may also include an indication of a maintenance schedule for the electric machine 105 based on the RUL of the bearing 102. For example, if the RUL of the bearing 102 drops below 100 hours, the notification may indicate that the electric machine 105 should be serviced within a specified time, such as within 3 days, to avoid failure.
[0085] The user interface can be configured to receive input for selecting an option to optimize the performance of the bearing 102 in response to the notification. For example, the user interface can display a notification "Do you want to optimize the performance of your 6203 bearing?", along with two tabs "Yes" and "No". The user can select the optimized bearing performance by selecting the tab "Yes" on the user interface using the input member. Otherwise, if the optimized bearing performance is not desired, the user can select the tab "No".
[0086] In an embodiment, the predicted RUL of the bearing 102 is used to adjust at least one control parameter of the electric machine 105 so that the RUL is optimized. The control parameter may be adjusted to modify the speed or load of the electric machine 105. For example, when the predicted RUL is below a threshold level, such as 100 hours, the adjustment of the control parameter is performed.
[0087] In an example, the control parameters may include the supply voltage, armature voltage, armature resistance, etc. in the case of a DC motor and the supply frequency in the case of an AC motor. More specifically, the control parameters are adjusted based on the application of the electric machine 105. For example, if the electric machine 105 is a motor used in a metal rolling operation, the speed can be reduced until a certain level at which the quality of the processed metal does not decrease beyond a threshold level. For example, the quality can be indicated by the accuracy relative to the desired thickness of the processed metal. In implementation, a list of options for the type of application and the desired quality level can be provided on the user interface. The user can further select the type of application and the desired quality level. In addition, based on the user's selection, the control parameters are identified from a lookup table stored in the database 195.
[0088] Furthermore, the RUL is recalculated based on known reliability analysis techniques.In a preferred embodiment, the RUL is estimated via simulation based on the Weibull cumulative damage model.
[0089] Figure 5 A graphical user interface 500 is shown which displays an example of a current spectrum generated based on the motor current signature. The current spectrum includes three spectral lines: a main component of 80 dB at 2792.4 Hz and two sidebands of 44 dB and 40 dB at (2792.4-59.4) Hz and (2792.4+59.4) Hz, respectively. Misalignment at lower frequencies is detected based on the following formula:
[0090] f e =f 1 +mf r (5).
[0091] Here,
[0092] f 1 is the power frequency;
[0093] f r is the rotor speed frequency;
[0094] m is the harmonic number (1, 2, 3..)
[0095] f e is the frequency of the current component due to the change in air gap.
[0096] Figure 6 A workflow 600 for estimating the RUL of a motor drive end bearing is shown according to an exemplary embodiment of the present invention.
[0097] At step 605, the virtual model is calibrated based on test data, which includes a current spectrum 610 for predefined misalignment values. More specifically, the calibration is used to reduce the deviation between the misalignment values generated via simulation based on the virtual model and the actual misalignment values in the test data at step 615. The virtual model is further updated based on operational data including a motor vibration spectrum 620 to reflect the real-time behavior of the motor. The dotted line between blocks 610 and 620 indicates the correlation between the current spectrum and the vibration spectrum, which can be determined using a regression algorithm, as explained earlier with reference to FIG. 3. At step 625, a simulation instance is generated based on the updated virtual model. The simulation instance is further executed in a simulation environment to generate simulation results indicating one or more real-time misalignment values associated with the pivot 107 of the motor.
[0098] Advantageously, a regression model that relates the current spectrum to the vibration spectrum enhances the detection of mechanical faults such as misalignment and eccentricity that could otherwise be detected using only the vibration signal.
[0099] At step 630, a dynamic misalignment force on the drive end bearing is calculated based on the misalignment value using a predetermined misalignment force model. At step 635, a RUL is determined based on the calculated dynamic misalignment force. At step 640, the RUL is further modified based on factors associated with contamination and lubrication associated with the bearing. In addition to the above, the misalignment value is provided as an output on a user interface associated with a user. As shown at step 645, the user can further provide input to the user interface to correct the misalignment. In addition, steps 630 to 640 are repeated for a new misalignment value corresponding to the corrected misalignment. Here, the RUL is calculated by a RUL model based on cumulative damage theory.
[0100] Figure 7 A workflow 700 for estimating the RUL of a motor drive end bearing according to another exemplary embodiment of the present invention is illustrated.
[0101] At step 705, real-time operational data is acquired from at least one sensing unit associated with the motor. At step 710, at least one feature associated with the real-time operational data is used to configure a simulation instance of a virtual model of the coupled system. The simulation instance is further executed in a simulation environment to determine a misalignment value. At step 715, a dynamic misalignment force caused by the misalignment is determined using a predetermined misalignment force model. In parallel, at step 720, a magnitude of a defect in the bearing caused by contamination and lubrication associated with the bearing is determined. For example, using Figure 3A and Figure 3B A second virtual model was trained using a similar approach as described in to calculate the size of defects caused by contamination and lubrication factors.
[0102] The contamination factor is determined based on the defect size. This is because defects in the bearing cause small, discrete particles of material to be removed from the bearing structure. These discrete particles increase the concentration of contaminants inside the bearing. The concentration of contaminants increases further as the defect size increases. The defect size is provided as an input to a trained classification model, which classifies the defect size into one of a plurality of severity levels. For example, a plurality of severity levels may correspond to "normal cleanliness", "slight to typical contamination", "severe contamination" and "very severe contamination". Based on the defect size, the trained classification model outputs a severity level. The severity level thus determined is further used to select an appropriate contamination factor from a second lookup table stored in the database 195. The second lookup table may include values of contamination factors corresponding to each severity level. Those skilled in the art must understand that the classification model may be trained to classify the defect size into one of any number of severity levels.
[0103] The viscosity ratio indicates the lubrication condition of the bearing during operation. The viscosity ratio is calculated as the ratio of the operating viscosity of the lubricant to the rated viscosity of the lubricant. The operating viscosity is calculated based on the viscosity grade of the lubricant and the operating temperature. The viscosity grade of the oil can be obtained from a third lookup table that includes viscosity grades corresponding to different types of lubricants. In one embodiment, the operating temperature of the bearing can be obtained from a temperature sensor associated with the bearing. In another embodiment, a virtual model of the bearing can be used to determine the thermal profile of the bearing based on the operating data. The rated viscosity is obtained from a fourth lookup table based on the bearing size and the bearing angular velocity.
[0104] At step 725, the maximum impact force is calculated using a predetermined impact force model that relates the defect size in the bearing to the maximum impact force in the rating life model:
[0105]
[0106] Here, the dynamic equivalent radial load P is the same as the maximum impact force calculated by the virtual model based on real-time operating data, while the other parameters are similar to those of equation (3). Figure 4 and Figure 6 As explained, the RUL based on the misalignment is estimated. At step 730, the cumulative RUL is estimated from the RUL estimated by equations (3) and (6) based on the cumulative damage theory. In addition, a notification indicating the cumulative RUL may be further generated on the output device.
[0107] Advantageously, the present invention facilitates online assessment of the effect of pivot misalignment on the remaining useful life of the bearings supporting the pivot. Thus, downtime associated with taking the electric machine offline to manually check for misalignment is reduced. Furthermore, a human operator can also make decisions about maintenance of the electric machine based on the remaining useful life provided via the output device.
[0108] The present invention is not limited to a specific computer system platform, processing unit, operating system or network. One or more aspects of the present invention can be distributed among one or more computer systems, and the one or more computer systems are, for example, servers configured to provide one or more services to one or more client computers or perform complete tasks in a distributed system. For example, according to various embodiments, one or more aspects of the present invention can be performed on a client-server system including components distributed among one or more server systems that perform multiple functions. These components include, for example, executable code, intermediate code or interpreted code, which communicate through a network using a communication protocol. The present invention is not limited to being executable on any particular system or system group, and is not limited to any particular distributed architecture, network or communication protocol.
[0109] Reference Symbols List
[0110] 100 Systems for estimating bearing RUL
[0111] 102 bearings
[0112] 105 Electric Machine
[0113] 107 Pivot
[0114] 110 Device for estimating the RUL of a bearing
[0115] 115 Edge Devices
[0116] 120 Network
[0117] 125 sensor units
[0118] 130 Client devices
[0119] 135 processing units
[0120] 140 memory cells
[0121] 145 storage units
[0122] 150 communication units
[0123] 155 Network Interface
[0124] 160 standard interface or bus
[0125] 165 Bearing Monitoring Module
[0126] 170 preprocessing module
[0127] 175 Analysis Module
[0128] 180 simulation module
[0129] 185 Life Estimation Module
[0130] 190 Notification Module
[0131] 195 Database
[0132] 200 ball bearings
[0133] 210 outer ring
[0134] 215 Multiple Balls 215
[0135] 220 cage 220
[0136] 225 inner circle
[0137] 305 Electric Motor
[0138] 310 Pump
[0139] 315 coupling
[0140] 320 drive pivot
[0141] 325 driven pivot
[0142] 330 Shell
[0143] 335 bearings
[0144] 340 Current Transformer
[0145] 345 Vibration Sensor
[0146] 350 devices
Claims
1. A computer-implemented method of estimating the remaining useful life of a bearing (102) of an electric machine (105), the electric machine (105) being operable to transfer rotational energy to a load via a pivot (107) supported by the bearing (102), the method comprising: obtaining, in real time, operational data associated with the electric machine (105) and indicative of misalignment of the pivot (107) from one or more sources (115, 125, 130); analyzing the operating data to detect misalignment of a pivot (107) of the electric machine (105); When the misalignment is detected, simulating the real-time behavior of at least the electric machine (105) using a virtual model of at least the electric machine (105) to achieve a simulation result indicating a misalignment value corresponding to the misalignment of the pivot (107); predicting a remaining useful life of a bearing (102) based on the misalignment value; A notification is generated on an output device indicating the predicted remaining useful life of the bearing (102).
2. The method according to claim 1, wherein: Analyzing the operational data to detect misalignment of the electric machine (105) pivot (107) includes: calculating a characteristic feature of the electric machine (105) based on the operating data; The characteristic features are analyzed to detect misalignment of the pivot (107).
3. The method according to claim 2, wherein: The characteristic feature is at least one of a current feature, a vibration feature, and a thermal feature.
4. The method according to claim 2 or 3, wherein: Characteristic features are generated from the operational data using one or more transformation functions.
5. The method according to claim 2, 3 or 4, wherein: Generate feature signatures based on operational data using regression models.
6. The method according to any one of claims 1 to 5, wherein: Using a virtual model of at least the electric machine (105) to simulate real-time behavior of at least the electric machine (105) to achieve a simulation result indicative of a misalignment value corresponding to a misalignment of the pivot (107), comprising: When misalignment is detected, dynamically updating a virtual model of at least the electric machine (105) based on the operational data; configuring at least a machine-executable simulation instance of the electric machine based on the updated virtual model; and The configured simulation instance is executed in the simulation environment to generate simulation results.
7. The method according to any one of claims 1 to 6, wherein: Predicting the remaining useful life of a bearing (102) based on the misalignment value includes: Calculating dynamic misalignment forces on the bearing (102) in real time based on the misalignment values using a predetermined misalignment force model; A rating life model for dynamically configuring a bearing (102) based on the calculated dynamic misalignment forces; and The remaining useful life of a bearing (102) is predicted using a configured rating life model.
8. The method according to any one of claims 1 to 7, further comprising: The predicted remaining useful life of the bearing (102) is used to adjust at least one control parameter of the electric machine (105).
9. The method according to claim 8, wherein: The at least one control parameter is adjusted to modify at least one of a speed and a load of the electric machine (105).
10. An apparatus (110) for estimating the remaining useful life of a bearing (102) associated with an electric machine (105), the apparatus (110) comprising: one or more processing units (135); and A memory unit (140) operably coupled to one or more processing units (135), wherein the memory unit (140) includes a bearing monitoring module (165) stored in the form of machine-readable instructions executable by the one or more processing units (135), wherein the bearing monitoring module (165) is configured to perform the method steps according to any one of claims 1 to 9.
11. A system (100) for estimating the remaining useful life of a bearing (102) associated with an electric machine (102), the system (100) comprising: one or more sources (115, 125, 130) configured to provide operational data associated with the electric machine (105); and The apparatus (110) of claim 10, being communicatively coupled to the one or more sources (115, 125, 130), wherein the apparatus (110) is configured for estimating a remaining useful life of the bearing (102) based on the operational data according to any one of method claims 1 to 9.
12. A computer program having machine-readable instructions which, when executed by one or more computing devices, cause the one or more computing devices to perform a method according to any one of claims 1 to 9.
13. A machine-readable storage medium comprising a computer program according to claim 12.
